Heh, that didn't occur to me. Indeed, that's a cause for celebration!
If they had included such goals, though, I'd be likely to stop donating money to them.
If they had included such goals, though, I'd be likely to stop donating money to them.
Not to mention being far slower to query.
Using embeddings basically lets the AI configure those things for you and auto updates when the AI updates.
You could also use the embeddings for far more advanced things like in LLMs, but the basic version that is just “better keyword search” is also valuable.
> Not to mention being far slower to query.
KNN on the embeddings is not obviously slower to query. In production using AWS ElasticSearch, for a very large search index, my team saw no meaningful change to latency when using embeddings instead.
If this is for my personal e-mail, then I'd only use it if it could run locally - which also means inobtrusively in the background, not slowing down my computer - is that feasible?
It's just someone having fun with generative AI to create few unique wallpapers and sharing them with their community.